© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8517
    Prev
    Next
    INDEX
    Explanations

    specific terminology or keywords associated with various subjects, including technology, sports, and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens appearing before a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    website names and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     telefónica
    -0.54
     navideño
    -0.42
    iální
    -0.41
     inmobili
    -0.40
     deportivo
    -0.40
     taşlı
    -0.40
     judiciaire
    -0.39
     flota
    -0.39
     eletrônico
    -0.37
     fís
    -0.37
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.68
    ValueStyle
    0.62
    /**
    0.62
    ьаж
    0.58
    AISSEE
    0.56
    RTLD
    0.55
     CRC
    0.54
    Билгалдахарш
    0.54
     TLV
    0.54
     XYZ
    0.53
    Activations Density 0.609%

    No Known Activations